First-episode schizofrenia classification with the use of MRI brain image deformations

SCHWARZ, Daniel, Eva JANOUŠOVÁ and Tomáš KAŠPÁREK. First-episode schizofrenia classification with the use of MRI brain image deformations. In Mezinároední workshop funkční magnetické rezonance. 2010.

Basic information

• Original name: First-episode schizofrenia classification with the use of MRI brain image deformations
• Authors: SCHWARZ, Daniel, Eva JANOUŠOVÁ and Tomáš KAŠPÁREK.
• Edition: Mezinároední workshop funkční magnetické rezonance, 2010.

Other information

• Type of outcome: Conference abstract
• Confidentiality degree: is not subject to a state or trade secret
• Organization unit: Faculty of Medicine
• Keywords (in Czech): MRI, deformace, rozpoznávání
• Keywords in English: MRI, DBM, deformations, recognition

Abstract

Deformation-based morphometry (DBM) has been used to uncover structural inter-group differences in MRI-based neuropsychiatric studies recently. We use 3-D deformation fields resulting from cross-subject registrations to construct classifiers which are able to recognize first-episode schizophrenia patients from healthy controls. The k-Nearest Neighbors (k-NN) and the Support Vector Machines (SVM) classification methods are compared in terms of their sensitivity, specificity and overall accuracy.

Abstract (in Czech)

Morfometrie založená na deformacích se používá k odhalení strukturálních skupinových rozdílů v MRI obrazech. Výsledné 3-D pole vychýlení jsou pak vstupem pro klasifikátory, kterými je možno rozpoznat první-epizody schizofrenie od zdravých kontrol. Jedná se o metody k-nejbližších sousedů (k-NN) a Support Vector Machines (SVM). Klasifikační metody jsou porovnány z hlediska jejich senzitivity, specificity a celkové přesnosti.

Abstract (in English)

Deformation-based morphometry (DBM) has been used to uncover structural inter-group differences in MRI-based neuropsychiatric studies recently. We use 3-D deformation fields resulting from cross-subject registrations to construct classifiers which are able to recognize first-episode schizophrenia patients from healthy controls. The k-Nearest Neighbors (k-NN) and the Support Vector Machines (SVM) classification methods are compared in terms of their sensitivity, specificity and overall accuracy.

Links

• NS10347, research and development project: Name: Moderní metody rozpoznávání pro analýzu obrazových dat v neuropsychiatrickém výzkumu

Investor: Ministry of Health of the CR

• NS9893, research and development project: Name: Predikce průběhu iniciálních fází schizofrenie pomocí morfologie mozku

Investor: Ministry of Health of the CR